RTID-08. MACHINE LEARNING TO UNCOVER SIGNATURES OF VULNERABILITY IN GLIOBLASTOMA UMBRELLA SIGNATURE TRIAL (GUST)

Glioblastoma is characterized by intra- and inter-tumoral heterogeneity. A glioblastoma umbrella signature trial (GUST) posits multiple investigational treatment arms based on corresponding biomarker signatures. A contingency of an efficient umbrella trial is a suite of orthogonal signatures to classify patients into the likely-most-beneficial arm. Assigning optimal thresholds of vulnerability signatures to classify patients as “most-likely responders” for each specific treatment arm is a crucial task. We utilized semi-supervised machine learning, Entropy-Regularized Logistic Regression, to predict vulnerability classification. By applying semi-supervised algorithms to the TCGA GBM cohort, we were able to transform the samples with the highest certainty of predicted response into a self-labeled dataset and thus augment the training data. In this case, we developed a predictive model with a larger sample size and potential better performance. Our GUST design currently includes four treatment arms for GBM patients: Arsenic Trioxide, Methoxyamine, Selinexor and Pevonedistat. Each treatment arm manifests its own signature developed by the customized machine learning pipelines based on selected gene mutation status and whole transcriptome data. In order to increase the robustness and scalability, we also developed a multi-class/label classification ensemble model that’s capable of predicting a probability of “fitness” of each novel therapeutic agent for each patient. Such a multi-class model would also enable us to rank each arm and provide sequential treatment planning. By expansion to four independent treatment arms within a single umbrella trial, a “mock” stratification of TCGA GBM patients labeled 56% of all cases into at least one “high likelihood of response” arm. Predicted vulnerability using genomic data from preclinical PDX models correctly placed 4 out of 6 models into the “responder” group. Our utilization of multiple vulnerability signatures in a GUST trial demonstrates how a precision medicine model can support an efficient clinical trial for heterogeneous diseases such as GBM. Surgical Therapies

CLRM-01. MACHINE LEARNING TO UNCOVER SIGNATURES OF VULNERABILITY IN GLIOBLASTOMA UMBRELLA SIGNATURE TRIAL (GUST)

Glioblastoma is characterized by intra- and inter-tumoral heterogeneity. A glioblastoma umbrella signature trial (GUST) posits multiple investigational treatment arms based on corresponding biomarker signatures. A contingency of an efficient umbrella trial is a suite of orthogonal signatures to classify patients into the likely-most-beneficial arm. Assigning optimal thresholds of vulnerability signatures to classify patients as “most-likely responders” for each specific treatment arm is a crucial task. We utilized semi-supervised machine learning, Entropy-Regularized Logistic Regression, to predict vulnerability classification. By applying semi-supervised algorithms to the TCGA GBM cohort, we were able to transform the samples with the highest certainty of predicted response into a self-labeled dataset and thus augment the training data. In this case, we developed a predictive model with a larger sample size and potential better performance. Our GUST design currently includes four treatment arms for GBM patients: Arsenic Trioxide, Methoxyamine, Selinexor and Pevonedistat. Each treatment arm manifests its own signature developed by the customized machine learning pipelines based on selected gene mutation status and whole transcriptome data. In order to increase the robustness and scalability, we also developed a multi-class/label classification ensemble model that’s capable of predicting a probability of “fitness” of each novel therapeutic agent for each patient. Such a multi-class model would also enable us to rank each arm and provide sequential treatment planning. By expansion to four independent treatment arms within a single umbrella trial, a “mock” stratification of TCGA GBM patients labeled 56% of all cases into at least one “high likelihood of response” arm. Predicted vulnerability using genomic data from preclinical PDX models correctly placed 4 out of 6 models into the “responder” group. Our utilization of multiple vulnerability signatures in a GUST trial demonstrates how a precision medicine model can support an efficient clinical trial for heterogeneous diseases such as GBM.

Drug-induced colitis on BRAF and MEK inhibitors for BRAF V600E-mutated non-small cell lung cancer: a case report

Summary Introduction. The combination of BRAF and MEK inhibitors has deeply changed the treatment of BRAF V600-mutant non-small cell lung cancer patients. These agents demonstrated high antitumor activity as well as safe and manageable toxicity profile. Hypertension, pyrexia and increased liver enzymes are the most common adverse events. Gastrointestinal toxicities are rare, and mainly consist of mild grade vomiting and diarrhea. Case report. We report the case of 70-year-old man affected by BRAF V600-mutant NSCLC with bilateral lung and bone metastases. First-line treatment with encorafenib (450 mg once daily) and binimetinib (45 mg twice daily) was administered within a clinical trial. At the first radiological assessment, computed tomography (CT) scan showed a partial response and signs of intestinal inflammation were reported. The investigational treatment was timely withheld. The subsequent colonoscopy demonstrated the presence of ulcerative lesions at the caecal tract, and the histological diagnosis suggested a drug-induced colitis. No specific treatment was given as the patient did not report abdominal disturbances. Forty-five days after treatment interruption a new CT scan showed the resolution of bowel inflammation and investigational treatment was resumed at the same doses. The patient is still alive and free of toxicity recurrence after 11 months from treatment initiation. Conclusion. Severe gastrointestinal toxicities are uncommon with BRAF and MEK inhibitors, although cases of colitis and intestinal perforation have already been reported in literature. The pathogenesis seems to be related to the MAPK pathway inhibition performed by MEK inhibitors. These adverse events should be accounted given the potential to evolve into life-threatening conditions.

The State of Neuro-Oncology During the COVID-19 Pandemic: A Worldwide Assessment

Background It remains unknown how the COVID-19 pandemic has changed neuro-oncology clinical practice, training and research efforts. Methods: We performed an international survey of practitioners, scientists, and trainees from 21 neuro-oncology organizations across 6 continents, April 24–May 17, 2020. We assessed clinical practice and research environments; institutional preparedness and support; and perceived impact on patients. Results Of 582 respondents, 258 (45%) were US-based, and 314 (55%) international. 94% participants reported changes in their clinical practice. 95% respondents converted at least some practice to telemedicine. 10% practitioners felt the need to see patients in person, specifically because of billing concerns and pressure from their institutions. 67% practitioners suspended enrollment for at least one clinical trial, including 62% suspending phase III trial enrollments. Over 50% believed neuro-oncology patients were at increased risk for COVID-19. 71% clinicians feared for their own personal safety or that of their families, specifically because of their clinical duties; 20% had inadequate PPE. While 69% reported increased stress, 44% received no psychosocial support from their institutions. 37% had salary reductions and 63% researchers temporarily closed their laboratories. However, the pandemic created positive changes in perceived patient satisfaction, communication quality, and technology use to deliver care and mediate interactions with other practitioners. Conclusions The pandemic has changed treatment schedules and limited investigational treatment options. Institutional lack of support created clinician and researcher anxiety. Communication with patients was satisfactory. We make recommendations to guide clinical and scientific infrastructure moving forward, and address the personal challenges of providers and researchers.

The Role of Physicians in Expanded Access to Investigational Drugs: A Mixed-Methods Study of Physicians’ Views and Experiences in The Netherlands

Treating physicians have key roles to play in expanded access to investigational drugs, by identifying investigational treatment options, assessing the balance of risks and potential benefits, informing their patients, and applying to the regulatory authorities. This study is the first to explore physicians’ experiences and moral views, with the aim of understanding the conditions under which doctors decide to pursue expanded access for their patients and the obstacles and facilitators they encounter in the Netherlands. In this mixed-methods study, semi-structured interviews (n = 14) and a questionnaire (n = 90) were conducted with medical specialists across the country and analysed thematically. Typically, our respondents pursue expanded access in “back against the wall” situations and broadly support its classic requirements. They indicate practical hurdles related to reimbursement, the amount of time and effort required for the application, and unfamiliarity with the regulatory process. Some physicians are morally opposed to expanded access, with an appeal to safety risks, lack of evidence, and “false hope.” Some of these moral concerns and practical obstacles may be essential targets for change, if expanded access to unapproved drugs is to become available for wider groups of patients for whom standard treatment options are not—or no longer—available, on a more consistent and equal basis.

Evolving to an Ideal Synthesis of Molnupiravir, an Investigational Treatment for COVID-19

<p>Molnupiravir (MK-4482) is an investigational direct-acting antiviral agent that is under development for the treatment of COVID-19. Given the potential high demand for this compound, it was critical to develop a sustainable and efficient synthesis from commodity raw materials. The three-step route that we report here embodies the shortest possible synthesis to molnupiravir, and was enabled through the invention of a novel biocatalytic cascade and final condensation step. Each step occurs in over 95% yield and only utilizes widely available commodity reagents and simple operations. Compared to the initial route, the new route is 70% shorter, and approximately seven-fold higher in overall yield. <br></p>

Evolving to an Ideal Synthesis of Molnupiravir, an Investigational Treatment for COVID-19

<p>Molnupiravir (MK-4482) is an investigational direct-acting antiviral agent that is under development for the treatment of COVID-19. Given the potential high demand for this compound, it was critical to develop a sustainable and efficient synthesis from commodity raw materials. The three-step route that we report here embodies the shortest possible synthesis to molnupiravir, and was enabled through the invention of a novel biocatalytic cascade and final condensation step. Each step occurs in over 95% yield and only utilizes widely available commodity reagents and simple operations. Compared to the initial route, the new route is 70% shorter, and approximately seven-fold higher in overall yield. <br></p>